CN116817537B - Multi-period refrigeration control method and system for refrigeration house based on external temperature measurement - Google Patents

Multi-period refrigeration control method and system for refrigeration house based on external temperature measurement Download PDF

Info

Publication number
CN116817537B
CN116817537B CN202311107165.4A CN202311107165A CN116817537B CN 116817537 B CN116817537 B CN 116817537B CN 202311107165 A CN202311107165 A CN 202311107165A CN 116817537 B CN116817537 B CN 116817537B
Authority
CN
China
Prior art keywords
temperature
period
temperature data
power
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202311107165.4A
Other languages
Chinese (zh)
Other versions
CN116817537A (en
Inventor
韩一博
李宗生
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Xingxing Refrigeration Technology Co Ltd
Original Assignee
Jiangsu Xingxing Refrigeration Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Xingxing Refrigeration Technology Co Ltd filed Critical Jiangsu Xingxing Refrigeration Technology Co Ltd
Priority to CN202311107165.4A priority Critical patent/CN116817537B/en
Publication of CN116817537A publication Critical patent/CN116817537A/en
Application granted granted Critical
Publication of CN116817537B publication Critical patent/CN116817537B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Devices That Are Associated With Refrigeration Equipment (AREA)

Abstract

The invention provides a multi-period refrigeration control method and system for a refrigeration house based on external temperature measurement, and relates to the technical field of refrigeration, wherein the method comprises the following steps: according to the first weather forecast data and the second temperature data outside the refrigeration house, correcting the temperature data outside the refrigeration house to obtain forecast temperature compensation parameters; obtaining external predicted temperature data according to the predicted temperature compensation parameter and the second weather predicted temperature; obtaining predicted refrigeration power according to refrigeration power, first temperature data, second temperature data, external predicted temperature data and set temperature in the ith period; and in the (i+1) th period, refrigerating the inside of the refrigeration house by predicting the refrigerating power. According to the invention, the weather forecast temperature can be compensated, so that the prediction accuracy of the external temperature of the refrigeration house is improved, and the refrigeration power can be timely adjusted under the condition of external temperature change, so that the refrigeration house can achieve an ideal refrigeration effect in time.

Description

Multi-period refrigeration control method and system for refrigeration house based on external temperature measurement
Technical Field
The invention relates to the technical field of refrigeration, in particular to a multi-period refrigeration house refrigeration control method and system based on external temperature measurement.
Background
In the refrigerating process of the refrigerator, the temperature outside the refrigerator has a certain influence on the refrigerating effect inside the refrigerator, for example, the influence of the heat exchange inside and outside the refrigerator on the refrigerating effect inside the refrigerator, the influence of the external environment of the refrigerator on the refrigerating cycle process of the refrigerating unit of the refrigerator and the like, and therefore, under different external environments, the refrigerating effect of the refrigerator may be influenced. In the related art, heat insulation materials are generally used for reducing heat exchange between the inside and the outside of the refrigerator, but the refrigerating power cannot be adjusted so as to achieve an ideal refrigerating effect in the refrigerator under different external temperature environments.
Disclosure of Invention
The invention provides a multi-period refrigeration control method and system based on external temperature measurement, which can solve the technical problem that the refrigeration power cannot be adjusted in time under the condition of external temperature change, so that the refrigeration house can achieve ideal refrigeration effect in time.
The multi-period refrigeration control method based on external temperature measurement comprises the following steps:
at a plurality of moments in the ith period, acquiring first temperature data in the refrigeration house through a first temperature sensor arranged in the refrigeration house, and acquiring second temperature data outside the refrigeration house through a second temperature sensor arranged outside the refrigeration house, wherein i is a positive integer;
Acquiring the set temperature in the refrigerator and the refrigeration power in the ith period;
acquiring a first weather forecast temperature of a geographic position of a cold storage in an ith period and a second weather forecast temperature of the cold storage in an (i+1) th period;
according to the first weather forecast data and the second temperature data, correcting deviation of temperature data outside the refrigeration house to obtain forecast temperature compensation parameters;
predicting the temperature outside the refrigerator in the (i+1) th period according to the predicted temperature compensation parameter and the second weather predicted temperature to obtain external predicted temperature data;
predicting the refrigeration power in the (i+1) th period according to the refrigeration power in the (i) th period, the first temperature data, the second temperature data, the external prediction temperature data and the set temperature to obtain predicted refrigeration power;
and in the (i+1) th period, refrigerating the inside of the refrigeration house through the predicted refrigerating power.
According to the first weather forecast data and the second temperature data, correcting the temperature data outside the refrigeration house to obtain forecast temperature compensation parameters, including:
according to the formula
Obtaining predicted temperature compensation parameters Wherein, the method comprises the steps of, wherein,superscript for second temperature data outside the refrigeration house at the jth moment in the ith periodIndicating the outside of the refrigeration house, n is eachThe number of moments in each period is j less than or equal to n, and j and n are positive integers,for the first weather forecast temperature, superscriptRepresenting a weather forecast.
Predicting the refrigeration power in the (i+1) th period according to the refrigeration power in the (i) th period, the first temperature data, the second temperature data, the external prediction temperature data and the set temperature to obtain a predicted refrigeration power, wherein the method comprises the following steps:
obtaining temperature difference data of each moment in an ith period according to the first temperature data and the second temperature data;
determining a temperature difference influence coefficient according to the temperature difference data, the refrigeration power in the ith period and the first temperature data;
training a power prediction model according to the temperature difference influence coefficient, the refrigeration power in the ith period, the first temperature data and the second temperature data, and obtaining a trained power prediction model;
and determining the predicted refrigeration power according to the external predicted temperature data, the set temperature, the first temperature data and the trained power prediction model.
Determining a temperature difference influence coefficient according to the temperature difference data, the refrigeration power in the ith period and the first temperature data, wherein the temperature difference influence coefficient comprises:
according to the formula
Determining a temperature difference influence coefficientWherein, the method comprises the steps of, wherein,as the temperature difference data at the kth time,is the temperature difference data at the (k+1) th moment, and is marked with a superscriptIndicating the difference between the inside and the outside of the refrigerator,is the first temperature data in the refrigeration house at the kth time in the ith period,the first temperature data in the refrigeration house at the (k+1) th moment in the ith period is marked by the upper markIndicating the interior of the refrigeration house,for the cooling power in the i-th period,for the interval duration between the various moments, n is the number of moments in each period, and k is a positive integer less than or equal to n-1.
Training a power prediction model according to the temperature difference influence coefficient, the refrigeration power in the ith period, the first temperature data and the second temperature data, and obtaining a trained power prediction model, wherein the training comprises the following steps:
determining a first temperature drop value between the first temperature data at the last time in the ith period and the 1 st first temperature data;
inputting the first temperature drop value, the temperature difference influence coefficient, the second temperature data and the first temperature data at the last moment in the ith period and the 1 st first temperature data into a power prediction model to obtain predicted power and predicted temperature data at a plurality of moments in the ith period;
Obtaining a loss function of a power prediction model according to the predicted power, the refrigeration power in the ith time period, the predicted temperature data at a plurality of moments in the ith time period and the first temperature data;
and training the power prediction model according to the loss function to obtain the trained power prediction model.
Obtaining a loss function of a power prediction model according to the predicted power, the refrigeration power in the ith time period, the predicted temperature data at a plurality of moments in the ith time period and the first temperature data, wherein the loss function comprises the following steps:
according to the formula
Obtaining a loss function L of the power prediction model, wherein,for the cooling power in the i-th period,for the predicted power, n is the number of times in each period,is the predicted temperature data at the t-th moment,is the predicted temperature data at time t+1st,is the predicted temperature data at time 2,is the predicted temperature data at the n-1 th moment,is the first temperature data in the refrigeration house at the t moment in the ith period,is the first temperature data in the refrigeration house at the 1 st moment in the ith period,is the first temperature data in the refrigeration house at the nth time in the ith period, In order to influence the coefficient of temperature difference,is the second temperature data outside the refrigeration house at the t moment in the ith period,is the second temperature data outside the refrigeration house at the t+1st moment in the ith period,is the second temperature data outside the refrigeration house at the 2 nd moment in the ith period,is the second temperature data outside the refrigeration house at the n-1 time in the ith period,for the duration of the interval between the various moments,is the temperature difference data at the t-th moment,as the temperature difference data at the nth time,is temperature difference data at the 1 st moment, t is a positive integer less than or equal to n-1,、、andis a preset weight.
Determining the predicted cooling power according to the external predicted temperature data, the set temperature, the first temperature data and a trained power prediction model, comprising:
determining a preset temperature drop value in the (i+1) th time period according to the first temperature data and the set temperature at the last moment in the (i) th time period;
and inputting a trained power prediction model according to the preset temperature drop value, the temperature difference influence coefficient, the external prediction temperature data and the first temperature data and the set temperature at the last moment in the ith period, and obtaining prediction temperature data at a plurality of moments in the (i+1) th period and prediction refrigeration power in the (i+1) th period.
The invention provides a multi-period refrigeration control system of a refrigeration house based on external temperature measurement, which comprises:
the measuring module is used for collecting first temperature data in the refrigeration house through a first temperature sensor arranged in the refrigeration house and collecting second temperature data outside the refrigeration house through a second temperature sensor arranged outside the refrigeration house at a plurality of moments in an ith time period, wherein i is a positive integer;
the acquisition module is used for acquiring the set temperature in the refrigerator and the refrigeration power in the ith period;
the forecasting module is used for acquiring a first weather forecast temperature of the geographic position of the freezer in the ith period and a second weather forecast temperature of the freezer in the (i+1) th period;
the compensation module is used for carrying out deviation correction processing on the temperature data outside the refrigeration house according to the first atmospheric forecast data and the second temperature data to obtain forecast temperature compensation parameters;
the external temperature prediction module is used for predicting the temperature outside the refrigeration house in the (i+1) th period according to the predicted temperature compensation parameter and the second weather predicted temperature to obtain external predicted temperature data;
the refrigeration power prediction module is used for predicting the refrigeration power in the (i+1) th period according to the refrigeration power in the (i) th period, the first temperature data, the second temperature data, the external prediction temperature data and the set temperature to obtain predicted refrigeration power;
And the refrigerating module is used for refrigerating the inside of the refrigeration house through the predicted refrigerating power in the (i+1) th period.
The compensation module is further configured to:
according to the formula
Obtaining predicted temperature compensation parametersWherein, the method comprises the steps of, wherein,superscript for second temperature data outside the refrigeration house at the jth moment in the ith periodIndicating the outside of the refrigerator, wherein n is the time quantity in each period, j is less than or equal to n, and j and n are positive integers,for the first weather forecast temperature, superscriptRepresenting a weather forecast.
The refrigeration power prediction module is further configured to:
obtaining temperature difference data of each moment in an ith period according to the first temperature data and the second temperature data;
determining a temperature difference influence coefficient according to the temperature difference data, the refrigeration power in the ith period and the first temperature data;
training a power prediction model according to the temperature difference influence coefficient, the refrigeration power in the ith period, the first temperature data and the second temperature data, and obtaining a trained power prediction model;
and determining the predicted refrigeration power according to the external predicted temperature data, the set temperature, the first temperature data and the trained power prediction model.
The refrigeration power prediction module is further configured to:
according to the formula
Determining a temperature difference influence coefficientWherein, the method comprises the steps of, wherein,as the temperature difference data at the kth time,is the temperature difference data at the (k+1) th moment, and is marked with a superscriptIndicating the difference between the inside and the outside of the refrigerator,is the first temperature data in the refrigeration house at the kth time in the ith period,the first temperature data in the refrigeration house at the (k+1) th moment in the ith period is marked by the upper markIndicating the interior of the refrigeration house,for the cooling power in the i-th period,for the interval duration between the various moments, n is the number of moments in each period, and k is a positive integer less than or equal to n-1.
The refrigeration power prediction module is further configured to:
determining a first temperature drop value between the first temperature data at the last time in the ith period and the 1 st first temperature data;
inputting the first temperature drop value, the temperature difference influence coefficient, the second temperature data and the first temperature data at the last moment in the ith period and the 1 st first temperature data into a power prediction model to obtain predicted power and predicted temperature data at a plurality of moments in the ith period;
Obtaining a loss function of a power prediction model according to the predicted power, the refrigeration power in the ith time period, the predicted temperature data at a plurality of moments in the ith time period and the first temperature data;
and training the power prediction model according to the loss function to obtain the trained power prediction model.
The refrigeration power prediction module is further configured to:
according to the formula
Obtaining a loss function L of the power prediction model, wherein,for the cooling power in the i-th period,for the predicted power, n is the time in each periodThe number of the etching steps,is the predicted temperature data at the t-th moment,is the predicted temperature data at time t+1st,is the predicted temperature data at time 2,is the predicted temperature data at the n-1 th moment,is the first temperature data in the refrigeration house at the t moment in the ith period,is the first temperature data in the refrigeration house at the 1 st moment in the ith period,is the first temperature data in the refrigeration house at the nth time in the ith period,in order to influence the coefficient of temperature difference,is the second temperature data outside the refrigeration house at the t moment in the ith period,is the second temperature data outside the refrigeration house at the t+1st moment in the ith period, Is the second temperature data outside the refrigeration house at the 2 nd moment in the ith period,for the (n-1) th time in the (i) th time periodIs a second temperature data outside the refrigerator,for the duration of the interval between the various moments,is the temperature difference data at the t-th moment,as the temperature difference data at the nth time,is temperature difference data at the 1 st moment, t is a positive integer less than or equal to n-1,、、andis a preset weight.
The refrigeration power prediction module is further configured to:
determining a preset temperature drop value in the (i+1) th time period according to the first temperature data and the set temperature at the last moment in the (i) th time period;
and inputting a trained power prediction model according to the preset temperature drop value, the temperature difference influence coefficient, the external prediction temperature data and the first temperature data and the set temperature at the last moment in the ith period, and obtaining prediction temperature data at a plurality of moments in the (i+1) th period and prediction refrigeration power in the (i+1) th period.
The invention can compensate the weather forecast temperature, thereby improving the prediction accuracy of the external temperature of the refrigeration house, and further adjusting the refrigeration power of the future period based on the actually measured temperature data inside and outside the refrigeration house and the predicted external prediction temperature data of the future period, so that the refrigeration power can be adjusted in time under the condition of external temperature change, and the refrigeration house can achieve ideal refrigeration effect in time. The ratio between the average value of the measured second temperature data and the predicted first temperature can be used for determining the predicted temperature compensation parameter, so that the prediction accuracy can be improved when the temperature outside the refrigerator in the future period is predicted. When the temperature difference influence coefficient is determined, the relation between the temperature decrease speed and the refrigeration power and temperature difference data can be determined by utilizing the correlation between the temperature decrease speed in the refrigerator and the refrigeration power and temperature difference data, and the temperature difference influence coefficient with higher accuracy can be determined by solving the average value of the relation in a plurality of time periods. When the power prediction model is trained, errors of the predicted power and the predicted temperature data can be reduced, and the predicted power and the predicted temperature data meet the constraint of the temperature difference influence coefficient, so that the accuracy of the power prediction model is improved, and the accuracy of the predicted power and the predicted temperature data is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as claimed. Other features and aspects of the present invention will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the invention or the solutions of the prior art, the drawings which are necessary for the description of the embodiments or the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments may be obtained from these drawings without inventive effort to a person skilled in the art,
fig. 1 schematically shows a flow chart of a multi-period refrigeration control method for a refrigeration storage based on external temperature measurement according to an embodiment of the invention;
fig. 2 schematically illustrates a multi-period refrigerator refrigeration control system based on ambient temperature measurement according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
Fig. 1 schematically shows a flow chart of a multi-period refrigeration control method based on external temperature measurement, according to an embodiment of the invention, the method includes:
step S101, collecting first temperature data in a refrigerator through a first temperature sensor arranged in the refrigerator and collecting second temperature data outside the refrigerator through a second temperature sensor arranged outside the refrigerator at a plurality of moments in an ith period, wherein i is a positive integer;
step S102, acquiring the set temperature in the refrigerator and the refrigeration power in the ith period;
step S103, acquiring a first weather forecast temperature of a geographic position of the freezer in an ith period and a second weather forecast temperature of the freezer in an (i+1) th period;
step S104, carrying out deviation correction processing on temperature data outside the refrigeration house according to the first atmospheric forecast data and the second temperature data to obtain forecast temperature compensation parameters;
step S105, according to the forecast temperature compensation parameter and the second weather forecast temperature, predicting the temperature outside the refrigerator in the (i+1) th period of time to obtain external prediction temperature data;
Step S106, the refrigeration power in the (i+1) th period is predicted according to the refrigeration power in the (i) th period, the first temperature data, the second temperature data, the external prediction temperature data and the set temperature, so as to obtain the predicted refrigeration power;
and step S107, refrigerating the inside of the refrigeration house through the predicted refrigerating power in the (i+1) th period.
According to the multi-period refrigeration control method based on external temperature measurement, disclosed by the embodiment of the invention, the weather forecast temperature can be compensated, so that the prediction accuracy of the external temperature of the refrigeration house is improved, the refrigeration power of the future period is regulated based on the actually measured internal and external temperature data of the refrigeration house and the predicted external predicted temperature data of the future period, and therefore, the refrigeration power can be regulated in time under the condition of external temperature change, and the refrigeration house can achieve an ideal refrigeration effect in time.
According to one embodiment of the invention, the temperature regulation of the interior of the refrigeration house is affected by the external temperature, for example, the temperature of the exterior of the refrigeration house is too high, heat exchange with the interior of the refrigeration house may be performed, refrigeration efficiency is affected, or heat dissipation of a condensing agent of the refrigeration unit may be affected, so that the efficiency of the refrigeration cycle is reduced. Therefore, the temperature inside and outside the refrigeration house can be measured in real time, so that the refrigeration power can be adjusted in time, and the proper refrigeration effect can be achieved.
According to one embodiment of the present invention, in step S101, a first temperature sensor may be provided inside the refrigerator and a second temperature sensor may be provided outside the refrigerator. At a plurality of times within each time period, first temperature data may be acquired by a first temperature sensor and second temperature data may be acquired by a second temperature sensor. Wherein the duration of each period may be 1 hour, 2 hours, etc., and the time interval between each time may be 30 seconds, 1 minute, etc., which the present invention is not limited to.
According to an embodiment of the present invention, in step S102, the set temperature inside the refrigerator and the cooling power in the i-th period may be acquired. In an example, a deviation between the set temperature and the first temperature data may be used to determine whether the cooling power in the i-th period is appropriate, for example, it may be determined whether the temperature inside the refrigerator is brought to the set temperature in the next period.
According to one embodiment of the present invention, in step S103, a first weather forecast temperature and a second weather forecast temperature for an i+1th period of time may be obtained for a geographic location where the freezer is located. The geographical position of the refrigerator can be a city, a county and the like where the refrigerator is located, the weather forecast data can be broadcast according to a time period, for example, temperature data between 9 and 10 am, temperature data between 14 and 15 pm and the like, and the first weather forecast temperature of the geographical position of the refrigerator in the ith time period and the second weather forecast temperature of the refrigerator in the (i+1) th time period can be inquired through the internet.
In step S104, according to an embodiment of the present invention, since the weather forecast data generally issues an average temperature of the area where the refrigerator is located, and is not accurate to a specific location where the refrigerator is located, there may be a deviation between an actual temperature outside the refrigerator and the first weather forecast temperature. Therefore, the second weather forecast temperature is expected to deviate from the measured temperature in the i+1th period. In order to overcome the problem, the forecast temperature compensation parameter can be solved based on the deviation between the second temperature data actually measured outside the refrigeration house in the ith period and the first weather forecast temperature, so that the second weather forecast temperature in the (i+1) th period is compensated, and the temperature forecast outside the refrigeration house in the (i+1) th period is more accurate.
According to one embodiment of the present invention, step S104 may include: obtaining a predicted temperature compensation parameter according to formula (1)，
（1）
Wherein,,for the jth period of timeSecond temperature data outside the refrigerator at moment, superscriptIndicating the outside of the refrigerator, wherein n is the time quantity in each period, j is less than or equal to n, and j and n are positive integers,for the first weather forecast temperature, superscriptRepresenting a weather forecast.
According to one embodiment of the present invention, the average value of the second temperature data outside the refrigerator at the j-th time in the i-th period, that is, And then the ratio between the average value and the first weather forecast temperature can be solved, and the ratio can be used as a forecast temperature compensation parameter for describing the proportional relation between the actual temperature outside the refrigeration house and the weather forecast temperature.
In this way, the ratio between the average value of the measured second temperature data and the first atmospheric forecast temperature can be used to determine the forecast temperature compensation parameter, so that the prediction accuracy can be improved when the temperature outside the refrigerator in the future period is predicted.
According to an embodiment of the present invention, in step S105, the external predicted temperature data in the i+1th period may be determined by the product of the second weather predicted temperature and the above predicted temperature compensation parameter, and it may be considered that the temperature outside the refrigerator remains unchanged in the i+1th period and is always equal to the external predicted temperature data.
According to one embodiment of the present invention, in step S106, the predicted cooling power in the i+1th period may be predicted so that the inside of the refrigerator may be adjusted to the set temperature in the i+1th period. That is, the refrigerating power can be adjusted in time under the condition that the refrigerating power in the ith period is not proper, and the proper refrigerating power in the (i+1) th period is obtained, so that the refrigerating effect is improved.
According to one embodiment of the present invention, step S106 may include: obtaining temperature difference data of each moment in an ith period according to the first temperature data and the second temperature data; determining a temperature difference influence coefficient according to the temperature difference data, the refrigeration power in the ith period and the first temperature data; training a power prediction model according to the temperature difference influence coefficient, the refrigeration power in the ith period, the first temperature data and the second temperature data, and obtaining a trained power prediction model; and determining the predicted refrigeration power according to the external predicted temperature data, the set temperature, the first temperature data and a trained power prediction model, wherein the power prediction model is a BP (Back Propagation) neural network model.
According to one embodiment of the present invention, the difference processing may be performed on the first temperature data and the second temperature data at each time in the ith period, and the temperature difference data at each time in the ith period may be obtained. The difference in temperature may have an influence on the cooling effect, and an influence of the temperature difference data on the cooling effect under the cooling effect of the cooling power in the ith period may be determined, for example, a change rule of the first temperature data, for example, a change speed of the first temperature data, etc. along with a change of the temperature difference data in the case that the cooling power is unchanged may be determined, so that an influence of the temperature difference data on the cooling effect may be determined.
According to an embodiment of the present invention, determining a temperature difference influence coefficient from the temperature difference data, the cooling power in the i-th period, and the first temperature data, includes: determining a temperature difference influence coefficient according to formula (2)，
（2）
Wherein,,as the temperature difference data at the kth time,is the temperature difference data at the (k+1) th moment, and is marked with a superscriptIndicating the difference between the inside and the outside of the refrigerator,is the first temperature data in the refrigeration house at the kth time in the ith period,the first temperature data in the refrigeration house at the (k+1) th moment in the ith period is marked by the upper markIndicating the interior of the refrigeration house,for the cooling power in the i-th period,for the interval duration between the various moments, n is the number of moments in each period, and k is a positive integer less than or equal to n-1.
According to one embodiment of the present invention, in equation (2),the average value of the temperature difference data representing the kth time and the kth+1 time can be used to represent the average temperature difference between the inside and outside of the refrigerator during the period between the kth time and the kth+1 time. And the greater the average temperature difference, the slower the rate of temperature decrease, i.e., the average temperature difference inversely correlates with the rate of temperature decrease, the rate of temperature decrease in the freezer can be determined by To represent. Further, the rate of temperature drop is proportional to the cooling power. Therefore, the temperature drop rate in the refrigerator is the refrigeration power in the time period between the kth time and the (k+1) th timeThe result of the positive correlation of the average value of the temperature difference data and the inverse correlation of the average value of the temperature difference data, that is, the temperature influence coefficient can be used to multiply the refrigerating power, and the ratio of the product to the temperature difference data can be solved, so that the temperature drop rate in the refrigeration house can be obtained. In other words, the temperature difference influence coefficient can be obtained by multiplying the temperature decrease rate by the average value of the temperature difference data and solving the ratio of the product to the cooling power. In order to improve the accuracy of the temperature difference influence coefficient, the average value of the ratios corresponding to n-1 time periods in the ith time period can be solved, and the temperature difference influence coefficient with higher accuracy can be obtained.
In this way, the correlation between the temperature drop speed and the refrigeration power and temperature difference data in the refrigerator can be utilized to determine the relationship between the temperature drop speed and the refrigeration power and temperature difference data, and the average value of the relationship in a plurality of time periods is solved to determine the temperature difference influence coefficient with higher accuracy.
According to an embodiment of the present invention, the power prediction model may be trained based on the above obtained temperature difference influence coefficient, and the cooling power, the first temperature data, and the second temperature data in the i-th period. The power prediction model may be trained once per time period to continuously adapt to the external and internal temperatures of the respective time periods, thereby obtaining more accurate predicted cooling power.
According to one embodiment of the present invention, training a power prediction model according to the temperature difference influence coefficient, the refrigeration power in the ith period, the first temperature data and the second temperature data, and obtaining a trained power prediction model includes: determining a first temperature drop value between the first temperature data at the last time in the ith period and the 1 st first temperature data; inputting the first temperature drop value, the temperature difference influence coefficient, the second temperature data and the first temperature data at the last moment in the ith period and the 1 st first temperature data into a power prediction model to obtain predicted power and predicted temperature data at a plurality of moments in the ith period; obtaining a loss function of a power prediction model according to the predicted power, the refrigeration power in the ith time period, the predicted temperature data at a plurality of moments in the ith time period and the first temperature data; and training the power prediction model according to the loss function to obtain the trained power prediction model.
According to one embodiment of the present invention, the first temperature decrease value may be obtained by subtracting the 1 st first temperature data from the first temperature data at the last time in the i-th period. After the first temperature decrease value is obtained, the first temperature decrease value, the temperature difference influence coefficient, the second temperature data, and the first temperature data at the last time in the ith period and the 1 st first temperature data can be input into a power prediction model, so that the power prediction model outputs predicted power, and the predicted power can enable the temperature in the refrigerator to decrease from the 1 st first temperature data to the first temperature data at the last time in the ith period under the influence of the temperature difference influence coefficient when the external temperature of the refrigerator is the second temperature data. And, the power prediction model may output predicted temperature data at a plurality of times in the i-th period, for calculation of the predicted temperature data, may be subjected to a temperature difference influence coefficient, a constraint of the second temperature data, and a constraint of predicted power, for example, for each of the predicted temperature data, a difference between it and the second temperature data may be calculated, and a rate of decrease of the predicted temperature data at an adjacent time may be calculated, and a relationship between the predicted temperature data, the difference between the predicted temperature data and the second temperature data, and the predicted power may be made to satisfy the constraint of the temperature difference influence coefficient, that is, a multiplication of the rate of decrease of the predicted temperature data, and the difference between the predicted temperature data and the second temperature data, and a ratio of the product and the predicted power may be solved, which is equal to the temperature difference influence coefficient.
According to an embodiment of the invention, the predicted temperature data and the predicted power obtained above may have errors, and the loss function of the power prediction model may be obtained according to the predicted power and the refrigeration power in the ith period, and the predicted temperature data and the first temperature data at a plurality of moments in the ith period, and training is performed based on the loss function, so that errors are reduced, and the accuracy of the power prediction model is improved.
Obtaining a loss function of a power prediction model according to the predicted power, the refrigeration power in the ith time period, the predicted temperature data at a plurality of moments in the ith time period and the first temperature data, wherein the loss function comprises the following steps: obtaining a loss function L of the power prediction model according to a formula (3),
（3）
wherein,,for the cooling power in the i-th period,for the predicted power, n is the number of times in each period,is the predicted temperature data at the t-th moment,
is the predicted temperature data at time t+1st,is the predicted temperature data at time 2,is the predicted temperature data at the n-1 th moment,is the first temperature data in the refrigeration house at the t moment in the ith period,
is the first temperature data in the refrigeration house at the 1 st moment in the ith period, Is the first temperature data in the refrigeration house at the nth time in the ith period,in order to influence the coefficient of temperature difference,
is the second temperature data outside the refrigeration house at the t moment in the ith period,is the second temperature data outside the refrigeration house at the t+1st moment in the ith period,is the second temperature data outside the refrigeration house at the 2 nd moment in the ith period,is the second temperature data outside the refrigeration house at the n-1 time in the ith period,
for the duration of the interval between the various moments,is the temperature difference data at the t-th moment,as the temperature difference data at the nth time,is temperature difference data at the 1 st moment, t is a positive integer less than or equal to n-1,、、andis a preset weight.
According to one embodiment of the present invention, the first term of the formula (3), which is a ratio between the deviation between the predicted power and the cooling power in the i-th period, is gradually reduced during training, so that the deviation between the predicted power and the cooling power in the i-th period is gradually reduced, and the accuracy of the predicted power is improved.
According to one embodiment of the present invention, the second term of the formula (3) is an average value of the ratio between the predicted temperature data from the 2 nd time to the n-1 th time and the first temperature data in the i-th time period, and the deviation from the first temperature data, and the first temperature data from the 1 st time and the last time in the i-th time period, and therefore, the predicted temperature data from the 1 st time and the last time in the i-th time period need not be predicted since the first temperature data from the 1 st time and the last time in the i-th time period has been input to the power prediction model. In the training process, the temperature prediction method is gradually reduced, so that deviation between the predicted temperature data and the measured first temperature data is gradually reduced, and accuracy of temperature prediction is improved.
According to one embodiment of the present invention, the third term of the formula (3) can be used to solve the predicted temperature data and the predicted power of the power prediction model, so as to satisfy the constraint of the temperature difference influence coefficient. In this term, since the first temperature data of the 1 st time and the last time in the ith time period has been input into the power prediction model without prediction, it can be determined based on this termDetermining whether the data in each of the time periods between the 2 nd to n-1 th times satisfies the constraint of the temperature difference influence coefficient, therefore, t may take a value between 2 and n-2, at t=2, it may be determined whether the data in the time period between the 2 nd to 3 rd times satisfies the constraint of the temperature difference influence coefficient, at t=3, it may be determined whether the data in the time period between the 3 rd to 4 th times satisfies the constraint of the temperature difference influence coefficient, and so on, at t=n-2, it may be determined whether the data in the time period between the n-2 th to n-1 th times satisfies the constraint of the temperature difference influence coefficient. In this item of description, the term "a" is used,the average value of the difference between the predicted temperature data at the t-th time and the second temperature data and the difference between the predicted temperature data at the t+1th time and the second temperature data can be used to represent the average temperature difference between the predicted temperature in the refrigerator and the measured temperature outside the refrigerator in the time period between the t-th time and the t+1th time. Is the rate of change of the predicted temperature in the refrigerator in the period between the t-th time and the t+1th time,the difference between the relation between the above data and the temperature difference influence coefficient may be expressed, and it may be expressed whether the above data satisfies the constraint of the temperature difference influence coefficient, and the smaller the difference, the more the data satisfies the constraint of the temperature difference influence coefficient, whereas the larger the difference, the less the data satisfies the constraint of the temperature difference influence coefficient. The average value of the differences can be solved, and in the training process, the average value is gradually reduced, so that the data in each time period meets the constraint of the temperature difference influence coefficient.
According to an embodiment of the present invention, the fourth term of the formula (3), which is similar to the third term, is used to enable the predicted temperature data and the predicted power solved by the power prediction model to satisfy the constraint of the temperature difference influence coefficient, is used to determine whether the data in the time period between the 1 st time and the 2 nd time in the i-th time period satisfies the constraint of the temperature difference influence coefficient, and whether the data in the time period between the n-1 st to the n-th time satisfies the constraint of the temperature difference influence coefficient. Since the power prediction model is input to both the first temperature data at the 1 st time and the first temperature data at the n-th time, the difference between the temperatures inside and outside the refrigerator can be solved by using the first temperature data at the 1 st time and the first temperature data at the n-th time. Likewise, during the training process, the term is scaled down gradually so that the data in each time period satisfies the constraint of the temperature difference influence coefficient.
According to one embodiment of the invention, the four items can be weighted and summed to obtain the loss function of the power prediction model, parameters of the power prediction model are adjusted through the loss function, so that the loss function is minimized, and the predicted power and the predicted temperature data obtained by the power prediction model meet the constraint of the temperature difference influence coefficient.
By the method, errors of the predicted power and the predicted temperature data can be reduced in the power prediction model training process, and the predicted power and the predicted temperature data meet the constraint of the temperature difference influence coefficient, so that the accuracy of the power prediction model is improved, and the accuracy of the predicted power and the predicted temperature data is improved.
According to one embodiment of the present invention, after training is completed, the trained power prediction model may be obtained, and determining the predicted cooling power according to the external predicted temperature data, the set temperature, the first temperature data, and the trained power prediction model includes: determining a preset temperature drop value in the (i+1) th time period according to the first temperature data and the set temperature at the last moment in the (i) th time period; and inputting a trained power prediction model according to the preset temperature drop value, the temperature difference influence coefficient, the external prediction temperature data and the first temperature data and the set temperature at the last moment in the ith period, and obtaining prediction temperature data at a plurality of moments in the (i+1) th period and prediction refrigeration power in the (i+1) th period.
According to one embodiment of the present invention, it may be considered that the temperature data outside the refrigerator at each time in the i+1th period is equal to the external predicted temperature data, and the set temperature is taken as the temperature data in the refrigerator at the last time in the i+1th period, and the first temperature data at the last time in the i+1th period is taken as the temperature data in the refrigerator at the 1 st time in the i+1th period, so that the preset temperature decrease value, the temperature difference influence coefficient, the external predicted temperature data, and the first temperature data and the set temperature at the last time in the i+1th period can be processed by the trained power prediction model, thereby obtaining the predicted temperature data at a plurality of times in the i+1th period, and the predicted cooling power in the i+1th period.
According to an embodiment of the present invention, in step S107, the predicted cooling power in the i+1th period obtained above may be used as the actual cooling power in the i+1th period to cool the refrigerator, so that the refrigerator may obtain a good cooling effect in the i+1th period, for example, at the end of the i+1th period, the temperature in the refrigerator may be reduced to the set temperature.
According to the multi-period refrigeration control method based on external temperature measurement, disclosed by the embodiment of the invention, the weather forecast temperature can be compensated, so that the prediction accuracy of the external temperature of the refrigeration house is improved, the refrigeration power of the future period is regulated based on the actually measured internal and external temperature data of the refrigeration house and the predicted external predicted temperature data of the future period, and therefore, the refrigeration power can be regulated in time under the condition of external temperature change, and the refrigeration house can achieve an ideal refrigeration effect in time. The ratio between the average value of the measured second temperature data and the predicted first temperature can be used for determining the predicted temperature compensation parameter, so that the prediction accuracy can be improved when the temperature outside the refrigerator in the future period is predicted. When the temperature difference influence coefficient is determined, the relation between the temperature decrease speed and the refrigeration power and temperature difference data can be determined by utilizing the correlation between the temperature decrease speed in the refrigerator and the refrigeration power and temperature difference data, and the temperature difference influence coefficient with higher accuracy can be determined by solving the average value of the relation in a plurality of time periods. When the power prediction model is trained, errors of the predicted power and the predicted temperature data can be reduced, and the predicted power and the predicted temperature data meet the constraint of the temperature difference influence coefficient, so that the accuracy of the power prediction model is improved, and the accuracy of the predicted power and the predicted temperature data is improved.
Fig. 2 schematically illustrates a schematic diagram of a multi-period refrigerator refrigeration control system based on external temperature measurement according to an embodiment of the present invention, as shown in fig. 2, the system includes:
the measuring module 101 is configured to collect, at a plurality of moments in an ith period of time, first temperature data in the refrigerator through a first temperature sensor disposed inside the refrigerator, and second temperature data outside the refrigerator through a second temperature sensor disposed outside the refrigerator, where i is a positive integer;
the obtaining module 102 is configured to obtain a set temperature inside the refrigerator and refrigeration power in an ith period;
a forecasting module 103, configured to obtain a first weather forecast temperature of the geographic location of the refrigerator in an i-th period and a second weather forecast temperature of the refrigerator in an i+1th period;
the compensation module 104 is configured to perform deviation correction processing on temperature data outside the refrigerator according to the first weather forecast data and the second temperature data, so as to obtain forecast temperature compensation parameters;
the external temperature prediction module 105 is configured to predict a temperature outside the refrigerator in an i+1th period according to the predicted temperature compensation parameter and the second weather predicted temperature, so as to obtain external predicted temperature data;
A refrigeration power prediction module 106, configured to predict the refrigeration power in the i+1th period according to the refrigeration power in the i period, the first temperature data, the second temperature data, the external prediction temperature data, and the set temperature, to obtain a predicted refrigeration power;
and the refrigerating module 107 is used for refrigerating the interior of the refrigeration house through the predicted refrigerating power in the (i+1) th period.
According to one embodiment of the invention, the compensation module is further configured to:
according to the formulaObtaining predicted temperature compensation parameters，
Wherein,,superscript for second temperature data outside the refrigeration house at the jth moment in the ith periodIndicating the outside of the refrigeration house,for the first weather forecast temperature, superscriptA weather forecast is indicated and the weather forecast is indicated,
n is the number of times in each period, j is less than or equal to n, and j and n are positive integers.
According to one embodiment of the invention, the refrigeration power prediction module is further configured to:
obtaining temperature difference data of each moment in an ith period according to the first temperature data and the second temperature data;
determining a temperature difference influence coefficient according to the temperature difference data, the refrigeration power in the ith period and the first temperature data;
Training a power prediction model according to the temperature difference influence coefficient, the refrigeration power in the ith period, the first temperature data and the second temperature data, and obtaining a trained power prediction model;
and determining the predicted refrigeration power according to the external predicted temperature data, the set temperature, the first temperature data and the trained power prediction model.
According to one embodiment of the invention, the refrigeration power prediction module is further configured to:
according to the formula
Determining a temperature difference influence coefficientWherein, the method comprises the steps of, wherein,as the temperature difference data at the kth time,is the temperature difference data at the (k+1) th moment, and is marked with a superscriptIndicating the difference between the inside and the outside of the refrigerator,is the first temperature data in the refrigeration house at the kth time in the ith period,the first temperature data in the refrigeration house at the (k+1) th moment in the ith period is marked by the upper markIndicating the interior of the refrigeration house,for the cooling power in the i-th period,for the interval duration between the various moments, n is the number of moments in each period, and k is a positive integer less than or equal to n-1.
According to one embodiment of the invention, the refrigeration power prediction module is further configured to:
Determining a first temperature drop value between the first temperature data at the last time in the ith period and the 1 st first temperature data;
inputting the first temperature drop value, the temperature difference influence coefficient, the second temperature data and the first temperature data at the last moment in the ith period and the 1 st first temperature data into a power prediction model to obtain predicted power and predicted temperature data at a plurality of moments in the ith period;
obtaining a loss function of a power prediction model according to the predicted power, the refrigeration power in the ith time period, the predicted temperature data at a plurality of moments in the ith time period and the first temperature data;
and training the power prediction model according to the loss function to obtain the trained power prediction model.
According to one embodiment of the invention, the refrigeration power prediction module is further configured to:
according to the formula
Obtaining a loss function L of the power prediction model, wherein,for the cooling power in the i-th period,for the predicted power, n is the number of times in each period,is the predicted temperature data at the t-th moment,is the predicted temperature data at time t+1st, Is the predicted temperature data at time 2,is the predicted temperature data at the n-1 th moment,is the first temperature data in the refrigeration house at the t moment in the ith period,is the first temperature data in the refrigeration house at the 1 st moment in the ith period,is the first temperature data in the refrigeration house at the nth time in the ith period,in order to influence the coefficient of temperature difference,is the second temperature data outside the refrigeration house at the t moment in the ith period,is the second temperature data outside the refrigeration house at the t+1st moment in the ith period,is the second temperature data outside the refrigeration house at the 2 nd moment in the ith period,is the second temperature data outside the refrigeration house at the n-1 time in the ith period,for the duration of the interval between the various moments,is the temperature difference data at the t-th moment,as the temperature difference data at the nth time,is temperature difference data at the 1 st moment, t is a positive integer less than or equal to n-1,、、andis a preset weight.
According to one embodiment of the invention, the refrigeration power prediction module is further configured to:
determining a preset temperature drop value in the (i+1) th time period according to the first temperature data and the set temperature at the last moment in the (i) th time period;
And inputting a trained power prediction model according to the preset temperature drop value, the temperature difference influence coefficient, the external prediction temperature data and the first temperature data and the set temperature at the last moment in the ith period, and obtaining prediction temperature data at a plurality of moments in the (i+1) th period and prediction refrigeration power in the (i+1) th period.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are by way of example only and are not limiting. The objects of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been shown and described in the examples and embodiments of the invention may be modified or practiced without departing from the principles described.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.

Claims (8)

1. The multi-period refrigeration control method for the refrigeration house based on the external temperature measurement is characterized by comprising the following steps of:
at a plurality of moments in the ith period, acquiring first temperature data in the refrigeration house through a first temperature sensor arranged in the refrigeration house, and acquiring second temperature data outside the refrigeration house through a second temperature sensor arranged outside the refrigeration house, wherein i is a positive integer;
acquiring the set temperature in the refrigerator and the refrigeration power in the ith period;
acquiring a first weather forecast temperature of a geographic position of a cold storage in an ith period and a second weather forecast temperature of the cold storage in an (i+1) th period;
according to the first atmospheric forecast temperature and the second temperature data, correcting deviation of temperature data outside the refrigeration house to obtain forecast temperature compensation parameters;
predicting the temperature outside the refrigerator in the (i+1) th period according to the predicted temperature compensation parameter and the second weather predicted temperature to obtain external predicted temperature data;
predicting the refrigeration power in the (i+1) th period according to the refrigeration power in the (i) th period, the first temperature data, the second temperature data, the external prediction temperature data and the set temperature to obtain predicted refrigeration power;
And in the (i+1) th period, refrigerating the inside of the refrigeration house through the predicted refrigerating power.
2. The method for controlling refrigeration of multi-period refrigerator based on external temperature measurement according to claim 1, wherein the performing deviation correction processing on temperature data outside the refrigerator according to the first atmospheric forecast temperature and the second temperature data to obtain forecast temperature compensation parameters comprises:
according to the formulaObtaining a forecast temperature compensation parameter->Wherein->The second temperature data outside the refrigerator at the jth moment in the ith period is marked with +.>Indicating the outside of the refrigerator->For the first weather forecast temperature, n is the time quantity in each period, j is less than or equal to n, j and n are positive integers, and the subscript is +.>Representing a weather forecast.
3. The method of claim 1, wherein predicting the cooling power in the i+1th period based on the cooling power in the i period, the first temperature data, the second temperature data, the external predicted temperature data, and the set temperature to obtain the predicted cooling power, comprises:
obtaining temperature difference data of each moment in an ith period according to the first temperature data and the second temperature data; determining a temperature difference influence coefficient according to the temperature difference data, the refrigeration power in the ith period and the first temperature data;
Training a power prediction model according to the temperature difference influence coefficient, the refrigeration power in the ith period, the first temperature data and the second temperature data, and obtaining a trained power prediction model;
and determining the predicted refrigeration power according to the external predicted temperature data, the set temperature, the first temperature data and the trained power prediction model.
4. The multi-period refrigerator cooling control method based on external temperature measurement according to claim 3, wherein determining a temperature difference influence coefficient from the temperature difference data, the cooling power in the i-th period, and the first temperature data, comprises:
according to the formula
Determining the temperature difference influence coefficient->Wherein->For the temperature difference data at the kth time, +.>Is the temperature difference data at the (k+1) th moment, and is marked with a superscriptIndicating the difference between the inside and outside of the freezer, +.>For the first temperature data of the interior of the freezer at the kth time in the ith period, +.>The first temperature data in the refrigeration house at the (k+1) th moment in the ith period is marked by +.>Indicating the interior of the refrigerator>For the cooling power in the ith period, < +.>For the interval duration between the various moments, n is the number of moments in each period, and k is a positive integer less than or equal to n-1.
5. The method of claim 3, wherein training a power prediction model based on the temperature difference influence coefficient, the cooling power in the i-th period, the first temperature data, and the second temperature data to obtain a trained power prediction model comprises:
determining a first temperature drop value between the first temperature data at the last time in the ith period and the 1 st first temperature data;
inputting the first temperature drop value, the temperature difference influence coefficient, the second temperature data and the first temperature data at the last moment in the ith period and the 1 st first temperature data into a power prediction model to obtain predicted power and predicted temperature data at a plurality of moments in the ith period;
obtaining a loss function of a power prediction model according to the predicted power, the refrigeration power in the ith time period, the predicted temperature data at a plurality of moments in the ith time period and the first temperature data;
and training the power prediction model according to the loss function to obtain the trained power prediction model.
6. The method of claim 5, wherein obtaining a loss function of a power prediction model based on the predicted power and the refrigeration power in the ith period, and the predicted temperature data and the first temperature data at a plurality of times in the ith period, comprises:
according to the formula
Obtaining a loss function L of the power prediction model, wherein +.>For the cooling power in the ith period, < +.>For the predicted power, n is the number of times in each period, < >>For the predicted temperature data at time t, < >>Is the predicted temperature data at time t+1st, and (2)>For the predicted temperature data at time 2, < +.>Is the predicted temperature data at the n-1 th moment,is the first temperature data of the interior of the refrigeration house at the t moment in the ith period +.>For the first temperature data of the interior of the freezer at time 1 in the ith period +.>For the first temperature data of the interior of the freezer at the nth time in the ith period +.>For the temperature difference influence coefficient, +.>Is the second temperature data of the outside of the refrigerator at the t moment in the ith period +.>Is the second temperature data of the outside of the refrigerator at the (t+1) th moment in the (i) th period, the temperature data of the outside of the refrigerator at the (t+1) th moment in the (i) th period >Is the second temperature data of the outside of the freezer at the 2 nd moment in the ith period +.>Is the second temperature data of the outside of the freezer at the n-1 th moment in the ith period,/for the cooling system>For the duration of the interval between the individual moments +.>For the temperature difference data at time t, < >>For the temperature difference data at the nth time, +.>Is the temperature difference data at the 1 st moment, t is a positive integer less than or equal to n-1,/h>、/>、/>And->Is a preset weight.
7. The multi-period refrigerator cooling control method based on external temperature measurement according to claim 3, wherein determining the predicted cooling power based on the external predicted temperature data, the set temperature, the first temperature data, and a trained power prediction model comprises:
determining a preset temperature drop value in the (i+1) th time period according to the first temperature data and the set temperature at the last moment in the (i) th time period;
and inputting a trained power prediction model according to the preset temperature drop value, the temperature difference influence coefficient, the external prediction temperature data and the first temperature data and the set temperature at the last moment in the ith period, and obtaining prediction temperature data at a plurality of moments in the (i+1) th period and prediction refrigeration power in the (i+1) th period.
8. Many periods freezer refrigeration control system based on ambient temperature measures, its characterized in that includes:
the measuring module is used for collecting first temperature data in the refrigeration house through a first temperature sensor arranged in the refrigeration house and collecting second temperature data outside the refrigeration house through a second temperature sensor arranged outside the refrigeration house at a plurality of moments in an ith time period, wherein i is a positive integer;
the acquisition module is used for acquiring the set temperature in the refrigerator and the refrigeration power in the ith period;
the forecasting module is used for acquiring a first weather forecast temperature of the geographic position of the freezer in the ith period and a second weather forecast temperature of the freezer in the (i+1) th period;
the compensation module is used for carrying out deviation correction processing on temperature data outside the refrigeration house according to the first atmospheric forecast temperature and the second temperature data to obtain forecast temperature compensation parameters;
the external temperature prediction module is used for predicting the temperature outside the refrigeration house in the (i+1) th period according to the predicted temperature compensation parameter and the second weather predicted temperature to obtain external predicted temperature data;
the refrigeration power prediction module is used for predicting the refrigeration power in the (i+1) th period according to the refrigeration power in the (i) th period, the first temperature data, the second temperature data, the external prediction temperature data and the set temperature to obtain predicted refrigeration power;
And the refrigerating module is used for refrigerating the inside of the refrigeration house through the predicted refrigerating power in the (i+1) th period.
CN202311107165.4A 2023-08-30 2023-08-30 Multi-period refrigeration control method and system for refrigeration house based on external temperature measurement Active CN116817537B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311107165.4A CN116817537B (en) 2023-08-30 2023-08-30 Multi-period refrigeration control method and system for refrigeration house based on external temperature measurement

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311107165.4A CN116817537B (en) 2023-08-30 2023-08-30 Multi-period refrigeration control method and system for refrigeration house based on external temperature measurement

Publications (2)

Publication Number Publication Date
CN116817537A CN116817537A (en) 2023-09-29
CN116817537B true CN116817537B (en) 2023-11-03

Family

ID=88127855

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311107165.4A Active CN116817537B (en) 2023-08-30 2023-08-30 Multi-period refrigeration control method and system for refrigeration house based on external temperature measurement

Country Status (1)

Country Link
CN (1) CN116817537B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001273007A (en) * 2000-03-27 2001-10-05 Osaka Gas Co Ltd Optimum driving control system of plant
CN103616733A (en) * 2013-11-28 2014-03-05 北京奇虎科技有限公司 Meteorological data acquisition and weather forecast method, device and system
CN108592515A (en) * 2018-06-04 2018-09-28 北京中冷高科制冷设备有限公司 A kind of control method of cold storage refrigerating system
CN109708258A (en) * 2018-12-20 2019-05-03 南京达实能源技术有限公司 A kind of temperature of ice house feedforward-Fuzzy control system and control method based on load dynamic change
CN111043731A (en) * 2019-12-31 2020-04-21 中维通(北京)科技有限公司 Air conditioning system adjusting method based on weather forecast
WO2020219608A1 (en) * 2019-04-22 2020-10-29 Lineage Logistics, LLC Scheduled thermal control system
TWI771224B (en) * 2021-11-10 2022-07-11 台灣松下電器股份有限公司 Smart temperature control system
CN116518640A (en) * 2023-07-05 2023-08-01 江苏星星冷链科技有限公司 Refrigerator control method, system and equipment

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001273007A (en) * 2000-03-27 2001-10-05 Osaka Gas Co Ltd Optimum driving control system of plant
CN103616733A (en) * 2013-11-28 2014-03-05 北京奇虎科技有限公司 Meteorological data acquisition and weather forecast method, device and system
CN108592515A (en) * 2018-06-04 2018-09-28 北京中冷高科制冷设备有限公司 A kind of control method of cold storage refrigerating system
CN109708258A (en) * 2018-12-20 2019-05-03 南京达实能源技术有限公司 A kind of temperature of ice house feedforward-Fuzzy control system and control method based on load dynamic change
WO2020219608A1 (en) * 2019-04-22 2020-10-29 Lineage Logistics, LLC Scheduled thermal control system
CN111043731A (en) * 2019-12-31 2020-04-21 中维通(北京)科技有限公司 Air conditioning system adjusting method based on weather forecast
TWI771224B (en) * 2021-11-10 2022-07-11 台灣松下電器股份有限公司 Smart temperature control system
CN116518640A (en) * 2023-07-05 2023-08-01 江苏星星冷链科技有限公司 Refrigerator control method, system and equipment

Also Published As

Publication number Publication date
CN116817537A (en) 2023-09-29

Similar Documents

Publication Publication Date Title
JP5658881B2 (en) Method for predicting the amount of electricity produced by photovoltaic power generation equipment
CN110705743A (en) New energy consumption electric quantity prediction method based on long-term and short-term memory neural network
KR102482043B1 (en) Method And Apparatus for Predicting Cooling Load in Small Scale Data
JP3783929B2 (en) Energy saving effect estimation method and apparatus
CN104517162A (en) On-line hardness forecasting method of continuous annealing product by means of integrated learning
JP2009294969A (en) Demand forecast method and demand forecast device
CN116518640B (en) Refrigerator control method, system and equipment
EP2944891B1 (en) Room temperature estimating device, program
JP4410046B2 (en) Apparatus and method for predicting heat load of air conditioning heat source facility
CN109657878A (en) A kind of Air-conditioning Load Prediction method and device
CN106650979A (en) Feeder baseline load prediction method
CN109523077B (en) Wind power prediction method
CN116753662A (en) Refrigerator partition control method and system
JPH0835706A (en) Air conditioning heat load predicting system
CN101482941A (en) Urban gas daily load prediction method
CN116817537B (en) Multi-period refrigeration control method and system for refrigeration house based on external temperature measurement
CN107194507A (en) A kind of short-term wind speed forecasting method of wind farm based on combination SVMs
CN114329347B (en) Method and device for predicting metering error of electric energy meter and storage medium
CN116451014A (en) Real-time monitoring method for temperature of movable part in wireless passive equipment
Kumar et al. Forecasting indoor temperature for smart buildings with ARIMA, SARIMAX, and LSTM: A fusion approach
Shirbhate et al. Solar panel monitoring and energy prediction for smart solar system
CN117610736A (en) Building cold and hot load prediction element learning modeling method for small sample data
JPH01300830A (en) Predictor for plant growth period
CN117200223A (en) Day-ahead power load prediction method and device
CN113033016B (en) Hybrid-based central air conditioner load prediction method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant